Understanding high-resolution climate analytics

Climate models have long struggled with coarse resolution, limiting precise climate risk insights. But AI-driven methods are now changing this, unlocking more detailed intelligence than traditional physics-based approaches. I recently spoke with a research scientist at Google Research who highlighted a promising new hybrid approach. This method combines physics-based General Circulation Models (GCMs) with AI refinement, significantly improving resolution. The process starts with Regional Climate Models (RCMs) anchoring physical consistency at ~45 km resolution. Then, it uses a diffusion model, R2-D2, to enhance output resolution to 9 km, making estimates more suitable for projecting extreme climate events. 🔥 About R2-D2 R2‑D2 (Regional Residual Diffusion-based Downscaling) is a diffusion model trained on residuals between RCM outputs and high-resolution targets. Conditioned on physical inputs like coarse climate fields and terrain, it rapidly generates high-res climate maps (~800 fields/hour on GPUs), complete with uncertainty estimates. ✅ Why this matters - Offers detailed projections of extreme climate events for precise risk quantification. - Delivers probabilistic forecasts, improving risk modeling and scenario planning. - Provides another high-resolution modeling approach, enriching ensemble strategies for climate risk projections. 👉 Read the full paper: https://lnkd.in/gU6qmZTR 👉 An excellent explainer blog: https://lnkd.in/gAEJFEV2 If your work involves climate risk assessment, adaptation planning, or quantitative modeling, how are you leveraging high-resolution risk projections?

In this week's column, I look at NVIDIA's new generative foundation model that it says enables simulations of Earth’s global climate with an unprecedented level of resolution. As is so often the case with powerful new technology, however, the question is what else humans will do with it. The company expects that climate researchers will build on top of its new AI-powered model to make climate predictions that focus on five-kilometer areas. Previous leading-edge global climate models typically don’t drill below 25 to 100 kilometers. Researchers using the new model may be able to predict conditions decades into the future with a new level of precision, providing information that could help efforts to mitigate climate change or its effects. A 5-kilometer resolution may help capture vertical movements of air in the lower atmosphere that can lead to certain kinds of thunderstorms, for example, and that might be missed with other models. And to the extent that high-resolution near-term forecasts are more accurate, the accuracy of longer-term climate forecasts will improve in turn, because the accuracy of such predictions compounds over time. The model, branded by Nvidia as cBottle for “Climate in a Bottle,” compresses the scale of Earth observation data 3,000 times and transforms it into ultra-high-resolution, queryable and interactive climate simulations, according to Dion Harris, senior director of high-performance computing and AI factory solutions at Nvidia. It was trained on high-resolution physical climate simulations and estimates of observed atmospheric states over the past 50 years. It will take years, of course, to know just how accurate the model’s long-term predictions turn out to be. The The Alan Turing Institute of AI and the Max Planck Institute of Meteorology, are actively exploring the new model, Nvidia said Tuesday at the ISC 2025 computing conference in Hamburg. Bjorn Stevens, director of the Planck Institute, said it “represents a transformative leap in our ability to understand, predict and adapt to the world around us.” The Earth-2 platform is in various states of deployment at weather agencies from NOAA: National Oceanic & Atmospheric Administration in the U.S. to G42, an Abu Dhabi-based holding company focused on AI, and the National Science and Technology Center for Disaster Reduction in Taiwan. Spire Global, a provider of data analytics in areas such as climate and global security, has used Earth-2 to help improve its weather forecasts by three orders of magnitude with regards to speed and cost over the last three or four years, according to Peter Platzer, co-founder and executive chairman.

📘 Downscaling CHIRPS Precipitation Data to 100m Resolution Using Sentinel-2 in Google Earth Engine Source Code = https://lnkd.in/dNc7NbjE 1. Introduction: Rainfall data at high spatial resolution is critical for precise hydrological analysis, drought monitoring, and agriculture planning. However, most global precipitation datasets, such as CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data), are available at coarser resolutions (~5 km). This project addresses this limitation by downscaling CHIRPS daily precipitation data to 100-meter spatial resolution using bilinear interpolation and Sentinel-2 as a high-resolution spatial reference. 2. Objective: To extract and sum CHIRPS precipitation data over a selected AOI (WMH District) for a specific 3-month period (October 2023 – January 2024). To downscale the CHIRPS raster data to a finer 100-meter resolution using Sentinel-2 spatial referencing. To visualize and compare the original and downscaled precipitation maps. To prepare refined precipitation layers for potential integration with NDVI, crop condition analysis, or drought indices. 3. Importance of the Study: Higher spatial resolution enables more localized analysis of rainfall, especially in heterogeneous landscapes. Improved input for climate models and agro-hydrological studies. Better decision-making for irrigation scheduling, water resource management, and drought preparedness. Supports integration with high-resolution datasets such as NDVI, land use, or soil moisture for multi-parameter environmental studies. 4. Benefits: Enhanced accuracy in rainfall data analysis at local and district levels. Scalable method applicable to any region globally. Supports policymakers and researchers with higher-resolution inputs for climate resilience, agricultural planning, and hydrological monitoring. Efficient use of cloud computing via Google Earth Engine for handling large spatiotemporal datasets. 5. Output: Original CHIRPS Precipitation Map (Oct 2023 – Jan 2024) clipped to WMH District. Downscaled Precipitation Map at 100m resolution, reprojected using Sentinel-2 reference. Color-coded visualization using a 5-class blue gradient, where: Light blue = Low precipitation Dark blue = High precipitation Ready-to-export raster layer of downscaled precipitation (if export added). Output maps can be further used for vegetation correlation (e.g., NDVI vs. rainfall) and SPI generation. #GEE #GoogleEarthEngine #BuildupAreaExpansion #GeospatialAnalytics #RemoteSensing #UrbanExpansion #Geospatial #GoogleEarthEngine #GIS #SustainableDevelopment #Sentinel2 #GeospatialTech #PhD #Agriculture #ClimateSmart #GIS #DeepLearning #ClimateSmartAgriculture #CropHealthMonitoring #DroughtMonitoring #SustainableFarming #Sentinel2 #GoogleEarthEngine #NDVI #LandsatData #GISMapping #GeospatialAnalysis #AIinAgriculture #EarthObservation #AgricultureMapping #RemoteSensin #SatelliteImagery

My IPCC journal - Storms... could hold important advances in AR7, thanks to the development of coordinated high-resolution (1-5km) regional climate simulations and projections. This is long awaited as we know that many impactful hazards are due to small-scale phenomena (eg. violent windstorms, extreme rainfalls, hailstorms, tropical cyclones, derechoes, ...), which are usually not resolved by climate models. Such models are also called "Convection-permitting Models" (CPMs). Five years ago, capacities (computing, model development, coordination) did not allow multi-model experiments with CPMs. Since then, coordinated initiatives in several regions took place. The AR7 report should be a home for assessing those experiments and what we are learning about climate change impacts on storms that will, for sure, be of high interest to society. Some papers: https://lnkd.in/eqWKUQKT https://lnkd.in/exdVq6y9 https://lnkd.in/eaY2p3vy 🌾High-resolution simulations differ from previous ones in that they are now explicitely resolving and large clouds due to convection, leading to thunderstorms and other severe weather conditions. Convective clouds include complex interactions between dynamical (winds) and thermodynamical (temperature, humidity, microphysics) processes, that can only be represented empirically in lower-resolution models. 🌾 Beyond processes, such models are expected to tell more about the effect of climate change in complex terrain (mountains, coasts, urban areas). For urban areas, this will also bring great material to our Special Report on Climate Change and Cities. 🌾As I stopped running myself regional climate simulations a few years ago and participating to ensemble regional climate experiments, I am personally eager to see the advances brought by my colleagues in this area. Please continue good work and papers! 🌾 IPCC, outreach: - TSUs continue developing a strategy for pre-scoping activities, meant to inform the AR7 scoping meeting, feeding it with expectations and ideas from stakeholders and representatives of research groups and organizations. A survey will soon be sent ot research organizations - For me this week was also filled with outreach activities. I met with a number of representatives of companies engaged in transition, and was happy to present the main results of AR6 and challenges for AR7, and exchange. This, in turn, triggered new requests for presentations (I will need to be careful about available time 😅). Through these discussions, I could measure the engagement of many in transition and in designing plans and strategies for decarbonization and value sharing. Transition cannot work if equity is left out of the scheme, internationally, and within companies as well. My presentations are always available from this link: 👉 https://lnkd.in/entCAewQ

𝗧𝗵𝗲 𝗶𝗺𝗽𝗮𝗰𝘁 𝗼𝗳 #𝗔𝗜 𝗼𝗻 𝗰𝗹𝗶𝗺𝗮𝘁𝗲 𝗽𝗿𝗲𝗱𝗶𝗰𝘁𝗶𝗼𝗻 𝗶𝘀 𝗵𝘂𝗴𝗲! 🚀 🥵 This year we are witnessing an exceptionally hot year on our Earth. And politicians discuss the future of climate action in the desert of #Dubai. 🧠Using deep learning #ai models allows scientists to better understand the impact of #climate change. The Problem: 🔢A numerical simulation of the climate covers a period of 50 to 200 years. Imagine a weather prediction model today covers up to 30 days. This forces the scientist to reduce the spatial and temporal resolution of the climate model to run the simulation on a cluster of computers. Operational #weather forecasts with a grid width of 1km (e.g. the Euro1k from Meteomatics ) up to 25km for global weather models like the GFS from NOAA: National Oceanic & Atmospheric Administration The climate model in the Karlsruher Institut für Technologie (KIT) study mentioned here has a grid of 32km. This makes it difficult to obtain changing patterns in severe weather due to climate change. Severe weather by thunderstorms are one of the most dangerous impact climate change. You can see the difference in the footage below. The Solution: 🕸️ To obtain local effects of climate change derived from climate models, the so-called downscaling approach is used. Usually these are also numerical algorithms. But Luca Glawion, Julius Polz, Harald Kunstmann, Benjamin Fresch, Christian Chwala find a way with a #neural #network called spateGAN. It is a spatial specification of a Generative Adversarial Network = GAN. 📊GANs have the ability to produce an ensemble output. That means the model generates multiple outputs. The number of simulations can be used to derive a probability distribution. Such forecasts are used to determine the probability of rain. The generator part of a GAN is usually a CNN (convolutional neural network), well known for image analysis and for the use in the first version of Siri. By the way, it is a German invention. Typically, climate model runs start 50 or 100 years back to compare with observations. This data can be used to fit/train the model and learn from high resolution observations such as radar. Such methods help us to estimate the impact of climate change and underline the strength we need to act on climate change. Direct link to the paper: https://lnkd.in/dWrCsvJS #cop28 #ipcc #meteorology #artifical #intelligence #cop #meteorology #numeric #machinelearning #ml